Time-Frequency Multiscale Convolutional Neural Network for RF-Based Drone Detection and Identification

Due to recent technological advancements and significant decreases in their costs, drones are gaining popularity rapidly. With drones becoming readily accessible to the public, the need for reliable detection and identification systems for drone networks is becoming more critical. We propose a time-frequency multiscale convolutional neural network-based deep learning model for the detection and identification of drones, which learns features from both raw and frequency domain drone radio frequency signals. The performance of the proposed network is evaluated on a publicly accessible database, and it outperforms state-of-the-art methods proposed for radio frequency-based drone detection and identification using deep neural networks.

Automated summary

Due to recent advancements in technology and cost reductions, drones are gaining popularity rapidly. With their increased accessibility, the need for reliable drone detection and identification systems is becoming more critical. In this study, we propose a deep learning model based on a time-frequency multiscale convolutional neural network to detect and identify drones using raw and frequency domain radio frequency signals. Our model outperforms state-of-the-art methods in drone detection and identification using deep neural networks, as evaluated on a publicly accessible database.